Training in progress, step 200, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 671149168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f403b11f0d3c12c04db99230e79c1b5f48a8ae7bc4676ce21362bce452ce869
|
| 3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1342555602
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:023b2352ca68be17aff455cdc0cf5d3f57a9dbbc2fbcf119d37df45c032f18a8
|
| 3 |
size 1342555602
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:caa1f41ed9a443e7226c7539bb539443b9e72f82223fab4b1ed7d9149a58eabe
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1089,6 +1089,364 @@
|
|
| 1089 |
"eval_samples_per_second": 6.979,
|
| 1090 |
"eval_steps_per_second": 3.49,
|
| 1091 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
@@ -1112,12 +1470,12 @@
|
|
| 1112 |
"should_evaluate": false,
|
| 1113 |
"should_log": false,
|
| 1114 |
"should_save": true,
|
| 1115 |
-
"should_training_stop":
|
| 1116 |
},
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
-
"total_flos":
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.06477297097444534,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.05739292632183084,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1089 |
"eval_samples_per_second": 6.979,
|
| 1090 |
"eval_steps_per_second": 3.49,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.04333165937298228,
|
| 1095 |
+
"grad_norm": 0.33814361691474915,
|
| 1096 |
+
"learning_rate": 1.9136088935510362e-05,
|
| 1097 |
+
"loss": 0.335,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.04361862400459143,
|
| 1102 |
+
"grad_norm": 0.40777504444122314,
|
| 1103 |
+
"learning_rate": 1.8414449687337464e-05,
|
| 1104 |
+
"loss": 0.3237,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.04390558863620059,
|
| 1109 |
+
"grad_norm": 0.3050004243850708,
|
| 1110 |
+
"learning_rate": 1.7703596875660645e-05,
|
| 1111 |
+
"loss": 0.3058,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.04419255326780974,
|
| 1116 |
+
"grad_norm": 0.29437223076820374,
|
| 1117 |
+
"learning_rate": 1.700377325606388e-05,
|
| 1118 |
+
"loss": 0.2735,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.0444795178994189,
|
| 1123 |
+
"grad_norm": 0.2806677520275116,
|
| 1124 |
+
"learning_rate": 1.631521781767214e-05,
|
| 1125 |
+
"loss": 0.3131,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.04476648253102805,
|
| 1130 |
+
"grad_norm": 0.22164231538772583,
|
| 1131 |
+
"learning_rate": 1.5638165701536868e-05,
|
| 1132 |
+
"loss": 0.2778,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.045053447162637206,
|
| 1137 |
+
"grad_norm": 0.21166081726551056,
|
| 1138 |
+
"learning_rate": 1.4972848120335453e-05,
|
| 1139 |
+
"loss": 0.2856,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.04534041179424636,
|
| 1144 |
+
"grad_norm": 0.338977187871933,
|
| 1145 |
+
"learning_rate": 1.4319492279412388e-05,
|
| 1146 |
+
"loss": 0.2946,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.045627376425855515,
|
| 1151 |
+
"grad_norm": 0.3277750611305237,
|
| 1152 |
+
"learning_rate": 1.3678321299188801e-05,
|
| 1153 |
+
"loss": 0.3168,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.04591434105746467,
|
| 1158 |
+
"grad_norm": 0.21984687447547913,
|
| 1159 |
+
"learning_rate": 1.3049554138967051e-05,
|
| 1160 |
+
"loss": 0.2944,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.046201305689073824,
|
| 1165 |
+
"grad_norm": 0.23201923072338104,
|
| 1166 |
+
"learning_rate": 1.2433405522156332e-05,
|
| 1167 |
+
"loss": 0.2733,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.04648827032068298,
|
| 1172 |
+
"grad_norm": 0.2661623954772949,
|
| 1173 |
+
"learning_rate": 1.183008586294485e-05,
|
| 1174 |
+
"loss": 0.2702,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.04677523495229213,
|
| 1179 |
+
"grad_norm": 0.39751991629600525,
|
| 1180 |
+
"learning_rate": 1.1239801194443506e-05,
|
| 1181 |
+
"loss": 0.2847,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.04706219958390129,
|
| 1186 |
+
"grad_norm": 0.2454085648059845,
|
| 1187 |
+
"learning_rate": 1.066275309832584e-05,
|
| 1188 |
+
"loss": 0.3029,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.047349164215510435,
|
| 1193 |
+
"grad_norm": 0.26145443320274353,
|
| 1194 |
+
"learning_rate": 1.0099138635988026e-05,
|
| 1195 |
+
"loss": 0.2737,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.04763612884711959,
|
| 1200 |
+
"grad_norm": 0.2140752375125885,
|
| 1201 |
+
"learning_rate": 9.549150281252633e-06,
|
| 1202 |
+
"loss": 0.2498,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.047923093478728744,
|
| 1207 |
+
"grad_norm": 0.36356833577156067,
|
| 1208 |
+
"learning_rate": 9.012975854638949e-06,
|
| 1209 |
+
"loss": 0.2556,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.0482100581103379,
|
| 1214 |
+
"grad_norm": 0.22013449668884277,
|
| 1215 |
+
"learning_rate": 8.490798459222476e-06,
|
| 1216 |
+
"loss": 0.2676,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.04849702274194705,
|
| 1221 |
+
"grad_norm": 0.29343363642692566,
|
| 1222 |
+
"learning_rate": 7.982796418105371e-06,
|
| 1223 |
+
"loss": 0.2885,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.04878398737355621,
|
| 1228 |
+
"grad_norm": 0.26217931509017944,
|
| 1229 |
+
"learning_rate": 7.489143213519301e-06,
|
| 1230 |
+
"loss": 0.2425,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.04907095200516536,
|
| 1235 |
+
"grad_norm": 0.2749157249927521,
|
| 1236 |
+
"learning_rate": 7.010007427581378e-06,
|
| 1237 |
+
"loss": 0.2684,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.04935791663677452,
|
| 1242 |
+
"grad_norm": 0.4522334635257721,
|
| 1243 |
+
"learning_rate": 6.5455526847235825e-06,
|
| 1244 |
+
"loss": 0.279,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.04964488126838367,
|
| 1249 |
+
"grad_norm": 0.3645327687263489,
|
| 1250 |
+
"learning_rate": 6.0959375958151045e-06,
|
| 1251 |
+
"loss": 0.2688,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.049931845899992826,
|
| 1256 |
+
"grad_norm": 0.36517390608787537,
|
| 1257 |
+
"learning_rate": 5.6613157039969055e-06,
|
| 1258 |
+
"loss": 0.2887,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.05021881053160198,
|
| 1263 |
+
"grad_norm": 0.23183710873126984,
|
| 1264 |
+
"learning_rate": 5.241835432246889e-06,
|
| 1265 |
+
"loss": 0.2649,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.050505775163211135,
|
| 1270 |
+
"grad_norm": 0.2555929720401764,
|
| 1271 |
+
"learning_rate": 4.837640032693558e-06,
|
| 1272 |
+
"loss": 0.2878,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.05079273979482029,
|
| 1277 |
+
"grad_norm": 0.19572857022285461,
|
| 1278 |
+
"learning_rate": 4.448867537695578e-06,
|
| 1279 |
+
"loss": 0.1717,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.051079704426429444,
|
| 1284 |
+
"grad_norm": 0.3167467415332794,
|
| 1285 |
+
"learning_rate": 4.075650712703849e-06,
|
| 1286 |
+
"loss": 0.2983,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.0513666690580386,
|
| 1291 |
+
"grad_norm": 0.25619232654571533,
|
| 1292 |
+
"learning_rate": 3.71811701092219e-06,
|
| 1293 |
+
"loss": 0.2628,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.05165363368964775,
|
| 1298 |
+
"grad_norm": 0.32165631651878357,
|
| 1299 |
+
"learning_rate": 3.376388529782215e-06,
|
| 1300 |
+
"loss": 0.2711,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.05194059832125691,
|
| 1305 |
+
"grad_norm": 0.32132670283317566,
|
| 1306 |
+
"learning_rate": 3.0505819692471792e-06,
|
| 1307 |
+
"loss": 0.2617,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.05222756295286606,
|
| 1312 |
+
"grad_norm": 0.3518334925174713,
|
| 1313 |
+
"learning_rate": 2.7408085919590264e-06,
|
| 1314 |
+
"loss": 0.2354,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.05251452758447522,
|
| 1319 |
+
"grad_norm": 0.4016975164413452,
|
| 1320 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 1321 |
+
"loss": 0.2265,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.052801492216084364,
|
| 1326 |
+
"grad_norm": 0.457795649766922,
|
| 1327 |
+
"learning_rate": 2.1697790249779636e-06,
|
| 1328 |
+
"loss": 0.21,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.05308845684769352,
|
| 1333 |
+
"grad_norm": 0.4268374741077423,
|
| 1334 |
+
"learning_rate": 1.908717841359048e-06,
|
| 1335 |
+
"loss": 0.2314,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.05337542147930267,
|
| 1340 |
+
"grad_norm": 0.5396208763122559,
|
| 1341 |
+
"learning_rate": 1.6640797865406288e-06,
|
| 1342 |
+
"loss": 0.2522,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.05366238611091183,
|
| 1347 |
+
"grad_norm": 0.39359378814697266,
|
| 1348 |
+
"learning_rate": 1.4359484041943038e-06,
|
| 1349 |
+
"loss": 0.2207,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.05394935074252098,
|
| 1354 |
+
"grad_norm": 0.43306687474250793,
|
| 1355 |
+
"learning_rate": 1.2244016009781701e-06,
|
| 1356 |
+
"loss": 0.2714,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.05423631537413014,
|
| 1361 |
+
"grad_norm": 0.5282922387123108,
|
| 1362 |
+
"learning_rate": 1.0295116199317057e-06,
|
| 1363 |
+
"loss": 0.3118,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.05452328000573929,
|
| 1368 |
+
"grad_norm": 0.39417564868927,
|
| 1369 |
+
"learning_rate": 8.513450158049108e-07,
|
| 1370 |
+
"loss": 0.2264,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.054810244637348446,
|
| 1375 |
+
"grad_norm": 0.39224889874458313,
|
| 1376 |
+
"learning_rate": 6.899626323298713e-07,
|
| 1377 |
+
"loss": 0.1956,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.0550972092689576,
|
| 1382 |
+
"grad_norm": 0.42377057671546936,
|
| 1383 |
+
"learning_rate": 5.454195814427021e-07,
|
| 1384 |
+
"loss": 0.221,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.055384173900566755,
|
| 1389 |
+
"grad_norm": 0.563609778881073,
|
| 1390 |
+
"learning_rate": 4.177652244628627e-07,
|
| 1391 |
+
"loss": 0.2169,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.05567113853217591,
|
| 1396 |
+
"grad_norm": 0.5513898134231567,
|
| 1397 |
+
"learning_rate": 3.0704315523631953e-07,
|
| 1398 |
+
"loss": 0.2839,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.055958103163785064,
|
| 1403 |
+
"grad_norm": 0.5315594673156738,
|
| 1404 |
+
"learning_rate": 2.1329118524827662e-07,
|
| 1405 |
+
"loss": 0.2911,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.05624506779539422,
|
| 1410 |
+
"grad_norm": 0.4934080243110657,
|
| 1411 |
+
"learning_rate": 1.3654133071059893e-07,
|
| 1412 |
+
"loss": 0.2298,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.05653203242700337,
|
| 1417 |
+
"grad_norm": 0.5377025604248047,
|
| 1418 |
+
"learning_rate": 7.681980162830282e-08,
|
| 1419 |
+
"loss": 0.2051,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.05681899705861253,
|
| 1424 |
+
"grad_norm": 0.6003627181053162,
|
| 1425 |
+
"learning_rate": 3.4146992848854695e-08,
|
| 1426 |
+
"loss": 0.1376,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.05710596169022168,
|
| 1431 |
+
"grad_norm": 0.5595711469650269,
|
| 1432 |
+
"learning_rate": 8.537477097364522e-09,
|
| 1433 |
+
"loss": 0.2216,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.05739292632183084,
|
| 1438 |
+
"grad_norm": 0.8547607064247131,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.2182,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.05739292632183084,
|
| 1445 |
+
"eval_loss": 0.06477297097444534,
|
| 1446 |
+
"eval_runtime": 841.5761,
|
| 1447 |
+
"eval_samples_per_second": 6.974,
|
| 1448 |
+
"eval_steps_per_second": 3.488,
|
| 1449 |
+
"step": 200
|
| 1450 |
}
|
| 1451 |
],
|
| 1452 |
"logging_steps": 1,
|
|
|
|
| 1470 |
"should_evaluate": false,
|
| 1471 |
"should_log": false,
|
| 1472 |
"should_save": true,
|
| 1473 |
+
"should_training_stop": true
|
| 1474 |
},
|
| 1475 |
"attributes": {}
|
| 1476 |
}
|
| 1477 |
},
|
| 1478 |
+
"total_flos": 5.1301336362673766e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|